kind: uapf.algorithm.card
id: algo.semantic_document_analysis.vdvc_semantic_extractor
version: 1.0.0
name: VDVC semantic metadata extractor
intent: |
  Extracts a VDVC v1.1-conformant structured semantic summary from the redacted document text — primary topic, keywords, classification, summary, sensitivity signals. Output validates against resources/schemas/vdvc-semantic-summary.schema.json. This is the sole model-inference step in the process; everything else in the package is deterministic.
algorithm_kind: extractor
io:
  inputs:
  - id: redacted_content
    type: string
    cardinality: single
    constraints:
      maxLength: 200000
    documentation: Output of the upstream PII redactor.
  - id: schema_ref
    type: string
    documentation: Path to the JSON Schema the output must validate against.
  outputs:
  - id: semantic_summary
    type: object
    schema: ../resources/schemas/vdvc-semantic-summary.schema.json
  - id: sensitivity_control
    type: object
  - id: ai_confidence_score
    type: probability
  - id: output_pii_error_count
    type: integer
    constraints:
      minimum: 0
implementation:
  type: external
  medium: llm_prompt
  uri: uapf-ip://capability/ai.extract@1
  hash: sha256:0000000000000000000000000000000000000000000000000000000000000000
  runtime:
    capability: ai.extract@1
    note: Host-fulfilled UAPF-IP capability. Specific model identity and prompt hash
      are runtime concerns of the host; the Card declares the contract, not the implementation
      choice.
determinism: stochastic
side_effects: external_call
confidence:
  type: probability
  threshold: 0.7
  below_threshold: route-to:human.legal_reviewer (enforced by DMN human-validation-gate)
complexity:
  typical_latency_ms: 8000
  max_latency_ms: 60000
failure_mode: default:null + flag — DMN human-validation-gate routes low-confidence
  outputs to PENDING_REVIEW.
limitations:
- Garie dokumenti (>50 000 znaki) tiek apgriezti — pirmie 50K + pēdējie 5K
- Nav juridisks vērtējums — tikai semantiska klasifikācija
- Latviešu valodas juridiskā retorika var samazināt recall
reference:
  legal: EU AI Act 2024/1689, Pielikums III (augstā riska MI sistēmas), 13. pants
    (caurspīdība).
  url: https://eur-lex.europa.eu/eli/reg/2024/1689/oj
owners:
- type: team
  id: uapf-stewards
  contact: stewards@uapf.dev
lifecycle:
  status: draft
  since: '2026-05-20'
audit:
  log_inputs: redacted
  log_outputs: full
  retention: 7y
risk:
  aiActRiskClass: high
  humanOversight: mandatory
  transparencyTier: tier-3-full
tests:
- name: Regulatory iesniegums about administrative decision
  description: Typical Latvian administrative complaint with redacted PII. The extractor
    should identify topic + risk + applicable regulation.
  inputs:
    redacted_content: Iesniedzējs [NAME] iesniedza sūdzību par būvvaldes lēmumu Nr.
      12345 atteikt būvatļauju adresē [ADDRESS]. Tiek lūgts pārskatīt lēmumu.
    schema_ref: schemas/iesniegums/v1
  expected_outputs:
    semantic_summary:
      topic: construction-permit-appeal
      subject_area: administrative-law
      applicable_regulations:
      - BL
      - APL
      language: lv
    sensitivity_control:
      contains_decision_reference: true
      external_communication_recommended: false
    ai_confidence_score: 0.87
    output_pii_error_count: 0
  tolerance:
    ai_confidence_score: 0.1
    output_pii_error_count: 0
- name: Non-regulatory thank-you note
  description: Out-of-domain input. Extractor should yield low-confidence summary
    and a sensitivity flag that no decision is referenced.
  inputs:
    redacted_content: Paldies par jūsu pakalpojumu! Bija ļoti patīkami sadarboties
      ar [NAME] no jūsu komandas.
    schema_ref: schemas/iesniegums/v1
  expected_outputs:
    semantic_summary:
      topic: non-actionable-correspondence
      subject_area: feedback
      applicable_regulations: []
      language: lv
    sensitivity_control:
      contains_decision_reference: false
      external_communication_recommended: false
    ai_confidence_score: 0.62
    output_pii_error_count: 0
  tolerance:
    ai_confidence_score: 0.15
    output_pii_error_count: 0